Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/feimacode/feima-copilot-llms-extension/copilot-instructionsgit clone --depth 1 https://github.com/feimacode/feima-copilot-llms-extensionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/feimacode/feima-copilot-llms-extension/copilot-instructions)<a href="https://agentmods.dev/instructions/feimacode/feima-copilot-llms-extension/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/feimacode/feima-copilot-llms-extension/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00425 | $0.00425 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
feima-copilot-llms-extension copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Feima Copilot LLMs Extension - Copilot Instructions
Localization
This extension has two separate and distinct localization systems. Do not mix them up.
1. Runtime strings — l10n/bundle.l10n.zh-cn.json
Used for strings displayed at runtime from TypeScript code via vscode.l10n.t().
Key rule: the key IS the full English string, not a short identifier.
// ✅ Correct — full English string as key
vscode.l10n.t('Signed in as {0}', session.account.label)
vscode.l10n.t('Please sign in to Feima first')
// ❌ Wrong — short identifier keys do NOT resolve to translations
vscode.l10n.t('error.signIn')
vscode.l10n.t('message.loggedIn')
When adding a new runtime string:
- Use the full English text as the
vscode.l10n.t()argument - Add the translation to
l10n/bundle.l10n.zh-cn.jsonwith the same full English string as the key:
{
"Signed in as {0}": "已登录为: {0}",
"Please sign in to Feima first": "请先登录 Feima 账号"
}
2. Manifest strings — package.nls.json / package.nls.zh-cn.json
Used only for static strings declared in package.json contributions (commands, settings, etc.) via %key% syntax.
// package.json
{ "title": "%command.signIn.title%" }
// package.nls.json (English default)
{ "command.signIn.title": "Sign In" }
// package.nls.zh-cn.json (Chinese translation)
{ "command.signIn.title": "登录" }
These keys are never used in TypeScript code. vscode.l10n.t('command.signIn.title') would display the literal string "command.signIn.title" — not the translation.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 50 lines · 425 tokens per session scan A db1fa43b472d
feima-copilot-llms-extension copilot-instructions.md is an instructions file published in the GitHub repository feimacode/feima-copilot-llms-extension (5 stars, last pushed 4d ago), licensed MIT. It adds 425 tokens to every session, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex-router CLAUDE.md
Claude Code instructions for duolahypercho/codex-router: Open and read AGENTS.md in full before installing, configuring, or extending this repository. It is the canonical instruction file for both Codex and Claude-based agents, including the procedures for adding local curated models, shipping repository-wide model…
FastGPT AGENTS.md
AGENTS.md instructions for labring/FastGPT, covering agents.md, 项目概述, 设计文档, 架构 and packages (库代码).
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
mazelingo CLAUDE.md
Instructions for Yeq6X/mazelingo, covering mazelingo, ビルド・開発, 構造 and ルール.
bob-plugin-ollama-translator CLAUDE.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
llm-ide-rules python-app.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering python app, factories and database & orm.